Borrowing it
Nothing to install: this file belongs to alphaaiservice/cortex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alphaaiservice/cortex/main/CLAUDE.mdgit clone --depth 1 https://github.com/alphaaiservice/cortexWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/alphaaiservice/cortex/claude-md)<a href="https://agentmods.dev/instructions/alphaaiservice/cortex/claude-md"><img src="https://agentmods.dev/badge/instructions/alphaaiservice/cortex/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/alphaaiservice/cortex/claude-md"><img src="https://agentmods.dev/badge/instructions/alphaaiservice/cortex/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.10295 | $0.10295 |
| Opus 5.5 | $0.04118 | $0.04118 |
| Sonnet 5.5 | $0.02059 | $0.02059 |
| Haiku 4.5 | $0.01030 | $0.01030 |
Grade B, and why
cortex CLAUDE.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Enable:** Set `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1` in `~/.claude/settings.json` under `"env"`. How it starts
The opening of the file, as written. The whole thing — 646 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Cortex Plugin Development Context
What Is This Project?
This is a Claude Code Plugin called cortex (Cortex) built by Alpha AI Service Pvt Ltd. It automates the entire software development lifecycle — from project scaffolding to autonomous product building — with zero human intervention.
The plugin enforces Alpha AI's engineering standards across 3 backend languages: Python/FastAPI, Node.js/NestJS, Java/Spring Boot — plus JWT+HTTP-Only Cookies (NEVER localStorage/sessionStorage), MySQL+ORM, MongoDB, Redis, and strict layer segregation.
Plugin Architecture
This is NOT a regular Python/Node project. It is a Claude Code Plugin — a collection of Markdown instruction files, bash scripts, and JSON configs that extend Claude Code's capabilities.
Directory Structure
cortex/
│
├── .claude-plugin/
│ ├── plugin.json # Plugin metadata (name, version, author)
│ └── marketplace.json # Marketplace catalog (for distribution via alphaaiservice/cortex)
│
├── commands/ # SLASH COMMANDS — user invokes with /command-name (55 total)
│ │
│ │ # ── Planning & Research ──
│ ├── gen-prd.md # /gen-prd — Generate PRD from brief idea
│ ├── gen-brand.md # /gen-brand — SVG logo & brand identity generation
│ ├── market-research.md # /market-research — Deep competitive analysis
│ ├── sprint-plan.md # /sprint-plan — Break PRD into sprint tasks with estimates
│ │
│ │ # ── Design & Media (v1.5.0) ──
│ ├── gen-mockup.md # /gen-mockup — UI screen mockups/wireframes as self-contained HTML/Next.js (brand-consistent, no API key)
│ ├── gen-pitch.md # /gen-pitch — Pitch/demo deck from PRD+research as Marp/Slidev markdown → PDF/HTML/PPTX
│ ├── gen-demo-video.md # /gen-demo-video — Product demo/marketing video as a Remotion project (script→TTS+captions→MP4)
│ │
│ │ # ── Project Setup ──
│ ├── init-project.md # /init-project — Scaffold new OR upgrade existing FastAPI/NestJS/Spring Boot project
│ ├── init-mcp-server.md # /init-mcp-server — Scaffold standalone MCP server (Python or TypeScript)
│ ├── init-claude-plugin.md # /init-claude-plugin — Scaffold a Claude Code plugin (dogfoods Cortex's own patterns)
│ ├── analyze-project.md # /analyze-project — Scan existing codebase, map architecture
│ ├── gap-analysis.md # /gap-analysis — Compare existing app vs Alpha AI 36 standards
│ ├── seed-data.md # /seed-data — Generate realistic seed/test data factories
│ │
│ │ # ── Building ──
│ ├── auto-build.md # /auto-build — Fully autonomous product builder (CORE)
│ ├── resume-build.md # /resume-build — Resume interrupted auto-build
│ ├── feature.md # /feature — Guided feature development
│ ├── retrofit.md # /retrofit — Add missing features to existing app
│ ├── migrate-stack.md # /migrate-stack — Safely migrate tech stack components
│ ├── refactor.md # /refactor — AI-powered code refactoring
│ ├── debug.md # /debug — AI-powered debugging and troubleshooting
│ │
│ │ # ── Quality & Testing ──
│ ├── code-review.md # /code-review — Automated multi-agent code review
│ ├── gen-tests.md # /gen-tests — Auto-generate unit/integration tests
│ ├── e2e-test.md # /e2e-test — Generate Playwright/Detox end-to-end tests
│ ├── perf-test.md # /perf-test — Performance/load testing with k6/Locust
│ ├── security-scan.md # /security-scan — SAST, DAST, secret detection, OWASP Top 10
│ ├── accessibility.md # /accessibility — WCAG 2.1 AA compliance audit
│ ├── tech-debt.md # /tech-debt — Scan and prioritize technical debt
│ ├── health-check.md # /health-check — Project health audit
│ │
│ │ # ── Shipping & Release ──
│ ├── ship.md # /ship — Lint → test → commit → push → create PR
│ ├── release.md # /release — Semver bump, changelog, git tag, GitHub Release
│ ├── changelog.md # /changelog — Auto-generate CHANGELOG.md from git history
│ ├── deploy.md # /deploy — Deploy with pre-flight checks
│ ├── gen-ci.md # /gen-ci — Generate CI/CD pipelines (GitHub Actions/GitLab/Bitbucket)
│ │
│ │ # ── Infrastructure & DevOps ──
│ ├── gen-infra.md # /gen-infra — Generate IaC (Docker, K8s, Terraform, Helm)
│ ├── db-migrate.md # /db-migrate — Database migration helper
│ ├── docker-clean.md # /docker-clean — Clean unused Docker resources
│ ├── monitoring.md # /monitoring — Prometheus + Grafana setup
│ ├── runbook.md # /runbook — Generate operational runbooks and playbooks
│ ├── backup-dr.md # /backup-dr — Automated backups, restore testing, DR runbooks
│ ├── env-sync.md # /env-sync — Environment parity checks, config drift, secret rotation
│ ├── feature-flags.md # /feature-flags — Feature flag system with MySQL + Redis + admin UI
│ ├── audit-setup.md # /audit-setup — Security audit logging, compliance, suspicious activity alerts
│ │
│ │ # ── Documentation & People ──
│ ├── gen-docs.md # /gen-docs — Generate README, Architecture, API, Deployment docs
│ ├── api-docs.md # /api-docs — Generate API documentation
│ ├── onboard-dev.md # /onboard-dev — Onboard new developer
│ │
│ │ # ── Analysis & Intelligence ──
│ ├── suggest-ai-features.md # /suggest-ai-features — Scan codebase, recommend AI/ML enhancements
│ ├── trace-impact.md # /trace-impact — Trace blast radius of a code change across full stack
│ ├── estimate-cost.md # /estimate-cost — Estimate infra + API costs at 3 scales
│ ├── feature-map.md # /feature-map — Build visual feature dependency map with Mermaid
│ ├── standup.md # /standup — Comprehensive task status across agents/teammates, background jobs, auto-build, sprint+Jira (READ-ONLY snapshot)
│ ├── ai-upgrade.md # /ai-upgrade — Implement AI capabilities on an existing feature
│ │
│ │ # ── Maintenance ──
│ ├── dep-update.md # /dep-update — Auto-update dependencies safely
│ │
│ │ # ── Cortex Cloud (auth + telemetry) ──
│ ├── cortex-login.md # /cortex-login — Authenticate plugin to Cortex Cloud (RFC 8628 device grant)
│ ├── cortex-logout.md # /cortex-logout — Revoke + clear local Cortex Cloud credentials
│ └── cortex-status.md # /cortex-status — Show Cortex Cloud connection + project status
│
├── agents/ # SUBAGENTS — spawned via Agent tool for parallel work (13 total)
│ ├── architect.md # Architecture analysis and design reviews
│ ├── brand-designer.md # SVG logo generation, color systems, brand identity
│ ├── security-auditor.md # Vulnerability scanning, secret detection
│ ├── onboarding-mentor.md # Interactive codebase Q&A for new devs
│ ├── test-strategist.md # Test coverage analysis and quality
│ ├── parallel-builder.md # Orchestrates parallel Agent subagents for speed
│ ├── self-healer.md # Auto-diagnoses and fixes errors during auto-build
│ ├── db-optimizer.md # Slow query analysis, missing indexes, N+1 detection
│ ├── devops-engineer.md # CI/CD, Docker, K8s, Terraform, deployment automation
│ ├── performance-profiler.md # API profiling, N+1 detection, bottleneck analysis
│ ├── documentation-writer.md # README, architecture docs, API reference, guides
│ ├── feature-analyzer.md # Codebase analysis, feature discovery, dependency mapping
│ └── ai-integration-specialist.md # AI/ML integration, LLM setup, vector search, cost tracking
│
├── skills/ # SKILLS — auto-invoked by Claude (Agent Skills open standard, 24 total)
│ ├── alpha-architecture/ # ⭐ MOST IMPORTANT — enforces tech stack + layer rules
│ │ ├── SKILL.md
│ │ └── references/
│ │ ├── CODE_PATTERNS_PYTHON.md # Python/FastAPI code patterns
│ │ ├── CODE_PATTERNS_NESTJS.md # NestJS/TypeScript code patterns
│ │ ├── CODE_PATTERNS_SPRINGBOOT.md # Java/Spring Boot code patterns
│ │ ├── CODE_PATTERNS_FRONTEND_PRODUCTION.md # ⭐ Frontend production bar: Fonts & Color (next/font + OKLCH tokens), Real data, Visual polish, Perf/A11y, Friendly errors (no HTTP codes/exceptions)
│ │ ├── CODE_PATTERNS_FRONTEND_CORE.md # Frontend Part 1: Dir structure, App Router, Routes, Providers, Middleware, Page State
│ │ ├── CODE_PATTERNS_FRONTEND_PAGES.md # Frontend Part 2: Dashboard Layout, 6 Page Templates (List/Detail/Form/Settings/Dashboard/Auth)
│ │ ├── CODE_PATTERNS_FRONTEND_UX.md # Frontend Part 3: Components, Responsive, Skeletons, SEO, Animations, Dark Mode, Cmd+K
│ │ ├── CODE_PATTERNS_CHROME_EXTENSION.md # Chrome Extension: MV3, Service Worker, Content Scripts, Messages, Storage, Security, AI Providers, Testing
│ │ ├── CODE_PATTERNS_GENAI.md # GenAI/LLM: LiteLLM gateway, prompts, agents, structured output, guardrails, caching (used by the genai skill)
│ │ ├── RAG_BEST_PRACTICES.md # RAG: chunking, embeddings, retrieval, re-ranking, agentic RAG, eval (used by the genai skill)
│ │ ├── LANG_PROFILE_PYTHON.md # Python stack: deps, dirs, configs, Docker
│ │ ├── LANG_PROFILE_NESTJS.md # NestJS stack: deps, dirs, configs, Docker
│ │ ├── LANG_PROFILE_SPRINGBOOT.md # Spring Boot stack: deps, dirs, configs, Docker
│ │ └── INFRA_HOSTINGER_K3S.md # Hostinger VPS + K3s: 4-node arch, Traefik, CI/CD, templates
│ ├── project-setup/
│ │ └── SKILL.md
│ ├── onboarding/
│ │ └── SKILL.md
│ ├── code-review/
│ │ └── SKILL.md
│ ├── testing/
│ │ └── SKILL.md
│ ├── deployment/
│ │ └── SKILL.md
│ ├── security/ # 🔒 Auto-enforces OWASP Top 10, auth, input validation, secrets
│ │ └── SKILL.md
│ ├── devops/ # 🐳 Auto-enforces Docker, CI/CD, K8s, monitoring standards
│ │ └── SKILL.md
│ ├── performance/ # ⚡ Auto-enforces DB optimization, caching, async patterns
│ │ └── SKILL.md
│ ├── frontend/ # 🎨 Auto-enforces the frontend production bar (fonts, OKLCH tokens, real data, polish, friendly errors) — refs CODE_PATTERNS_FRONTEND_*
│ │ └── SKILL.md
│ ├── genai/ # 🤖 Auto-enforces AI engineering (LiteLLM gateway, guardrails, cost caps, structured output, RAG, evals) — refs CODE_PATTERNS_GENAI + RAG_BEST_PRACTICES
│ │ └── SKILL.md
│ ├── accessibility/ # ♿ Auto-enforces WCAG 2.1 AA at authoring time (semantic HTML, ARIA, contrast, keyboard nav, focus)
│ │ └── SKILL.md
│ ├── database/ # 🗄️ Auto-enforces safe reversible zero-downtime migrations, datastore selection, repository boundary
│ │ └── SKILL.md
│ ├── mockup/ # 🖼️ Auto-invoked on "mock up / wireframe a screen" — brand-consistent screens as code (paired with /gen-mockup)
│ │ └── SKILL.md
│ ├── pitch-deck/ # 📊 Auto-invoked on "pitch deck / slides / presentation" — Marp/Slidev → PDF/HTML/PPTX (paired with /gen-pitch)
│ │ └── SKILL.md
│ ├── video-producer/ # 🎬 Auto-invoked on "demo / marketing video" — Remotion project, TTS voiceover + captions (paired with /gen-demo-video)
│ │ └── SKILL.md
│ │ # (also: cost-estimator, dependency-mapper, feature-impact-analysis, metric-recommender, smart-retrofit — analysis & advisory;
│ │ # cortex-brainstorming, cortex-planning, cortex-tdd, cortex-debugging, cortex-verification — meta-process)
│ └── jira-integration/ # 🟦 Auto-invoked on Jira work — bidirectional sync via Atlassian MCP (NO command)
│ └── SKILL.md
│
├── .mcp.json # MCP SERVERS Cortex CONSUMES — atlassian (Jira/Confluence) via official remote MCP
│
├── hooks/ # HOOKS — event-driven automation
│ └── hooks.json # Defines when hooks fire and what they do
│
├── scripts/ # BASH SCRIPTS — executed by hooks or standalone
│ ├── auto-loop.sh # Persistent Ralph Loop runner (shell-level)
│ ├── auto-build-stop-hook.sh # Stop hook: prevents exit during auto-build
│ ├── session-context.sh # SessionStart hook: loads project context + emits the SKILL PRECEDENCE directive (see below)
│ └── safe-bash-check.sh # PreToolUse hook: warns on dangerous commands
│
├── README.md
├── LICENSE
└── CLAUDE.md # ← THIS FILE
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 646 lines · 10,295 tokens per session scan B d6bea3e69617
cortex CLAUDE.md is an instructions file published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 2mo ago), licensed MIT. It adds 10,295 tokens to every session, about $0.0412 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.